-
2025The instruction hierarchy, which establishes a priority order from system messages to user messages, conversation history, and tool outputs, is essential for ensuring consistent and safe behavior in language models (LMs). Despite its importance, this topic receives limited attention, and there is a lack of comprehensive benchmarks for evaluating models’ ability to follow the instruction hierarchy. We bridge
-
2025Retrieval-Augmented Generation (RAG) systems have shown promise in enhancing the performance of Large Language Models (LLMs). However, these systems face challenges in effectively integrating external knowledge with the LLM’s internal knowledge, often leading to issues with misleading or unhelpful information. This work aims to provide a systematic study on knowledge checking in RAG systems. We conduct
-
2025Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit from a second pass rescoring using LLM. Recently multi-modal large language models, particularly speech and text foundational models have demonstrated strong spoken language
-
2025Target Speech Extraction (TSE) traditionally relies on explicit clues about the speaker’s identity like enrollment audio, face images, or videos, which may not always be available. In this paper, we propose a text-guided TSE model StyleTSE that uses natural language descriptions of speaking style in addition to the audio clue to extract the desired speech from a given mixture. Our model integrates a speech
-
2025Products on e-commerce platforms are usually organized based on seller-provided product attributes. Customers looking for a product typically have certain needs or use cases in mind, such as headphones for gym classes, or a printer for school projects. However, they often struggle to map these use cases to product attributes, thereby failing to find the product they need. To help customers shop online confidently
Related content
-
January 26, 2021Sneha Rajana is an applied scientist at Amazon today, but she didn't start out that way. Learn how she made the switch, and the advice she has for others considering a similar change.
-
January 25, 2021New approach to few-shot learning improves on state of the art by combining prototypical networks with data augmentation.
-
January 21, 2021Amazon principal applied scientist Yang Liu on the frontiers of speech and dialogue.
-
January 13, 2021In experiments, multilingual models outperform monolingual models.
-
December 18, 2020Researchers propose a method to automatically generate training data for Alexa by identifying cases in which customers rephrase unsuccessful requests.
-
December 14, 2020Parallel speech recognizers, language ID, and translation models geared to conversational speech are among the modifications that make Live Translation possible.